Skip to main content
Glama

Retry a job

retry_job

Rerun a failed or cancelled document job using its saved settings and source to recover the result; confirm credit usage before starting.

Instructions

Run a failed or cancelled document job again with the same settings, from its stored source (kept about 7 days). Pass document_path to wait and save the result there, as the other tools do. COSTS CREDITS like the original job - say so and get agreement first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "job_id": "<job_id>"
    },
    "name": "retry_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYesThe failed or cancelled job to run again
output_pathNoWhere to write the result
wait_secondsNoHow long to wait before returning (default 55)
document_pathNoThe original document, so the result is saved beside it and named after it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations, which only say this is a non-read-only, non-destructive operation. The description discloses the credit cost, the requirement to obtain user agreement first, the ~7-day source retention window that limits retryability, and that passing document_path makes the call block and save output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and eligibility, then the path behavior, then the cost warning in caps. Little waste, though the document_path sentence spends words on a distinction the schema also muddies.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers cost, retention, waiting and path behavior for a mutation tool with thin annotations. With no output schema, however, the description never says what comes back from a retry (a new job id, the same id, immediate status), which an agent needs to chain a follow-up call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds the behavioral link that document_path triggers waiting and result placement, but it does so while the schema also exposes a separate output_path 'Where to write the result', leaving the difference between those two paths implicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a failed or cancelled document job again') plus the key scope constraint: it reuses 'the same settings' and the stored source. An agent can distinguish this from check_job, cancel_job or condense_document without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly frames the eligible precondition (job must be failed or cancelled) and adds a procedural requirement ('say so and get agreement first'). It does not explicitly point at a sibling alternative for live jobs, so it falls short of a full when/when-not routing statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.